dzhng

Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo

Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.

Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.

Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.

Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it

Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec`, ONLY when the user expli…

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits

Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, legacy leftovers, changed scope, or when a change reveals duplicated concepts, local adapters, obsolete owners, redundant inputs or guards, compatibility wrappers, parallel abstractions, an over-large…